You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Contextual layers in ATIP could emphasize nearby POIs -- shops, public spaces, big transport hubs, greenspace, etc. We should think through how to visualize this, and how much we could auto-score new routes drawn based on what types of amenities it passes by. We can also think about this in context of improving access to amenities.
See https://dabreegster.github.io/talks/tds_seminar_synthpop/slides.html#/trip-attractor-tables-for-destinations for very vague notes about using this kind of data with a travel demand modeling. Instead of equally weighting a corner store and a big supermarket for the activity of grocery shopping, we could maybe use some kind of ML (if we have data on what types of shops people actually visit?) to tune weights more specifically.
The silly codename previously used for this: DestAny
The text was updated successfully, but these errors were encountered:
Contextual layers in ATIP could emphasize nearby POIs -- shops, public spaces, big transport hubs, greenspace, etc. We should think through how to visualize this, and how much we could auto-score new routes drawn based on what types of amenities it passes by. We can also think about this in context of improving access to amenities.
See https://dabreegster.github.io/talks/tds_seminar_synthpop/slides.html#/trip-attractor-tables-for-destinations for very vague notes about using this kind of data with a travel demand modeling. Instead of equally weighting a corner store and a big supermarket for the activity of grocery shopping, we could maybe use some kind of ML (if we have data on what types of shops people actually visit?) to tune weights more specifically.
The silly codename previously used for this: DestAny
The text was updated successfully, but these errors were encountered: